AI-Augmented Advances in the Diagnostic Approaches to Endometrial Cancer

Abstract

Background: Endometrial cancer (EC) is the most common gynecological malignancy in developed countries, with diagnostic accuracy and early detection being critical to patient outcomes. Recent advances in artificial intelligence (AI) offer new opportunities to enhance diagnostic precision and clinical decision-making. Objectives: This literature review aims to explore recent developments in AI-augmented diagnostic approaches for EC, with a focus on applications in histopathology, imaging, and multi-omics, and to assess their clinical impact and future potential. Methods: A non-systematic literature review was conducted to examine recent advances in artificial intelligence applications for the diagnosis of EC. Relevant studies were identified through searches on PubMed and Google Scholar, focusing on the integration of AI techniques in histopathology, imaging, and multi-omics data. Conclusions: AI-driven diagnostic tools have shown high performance in detecting and characterizing EC across multiple modalities, often matching or exceeding expert-level accuracy. These technologies hold promise for earlier detection, better risk assessment, and more personalized treatment planning. However, further research and validation are needed to address current limitations and support their broader integration into clinical workflows.